AI Paper Atlas

Research map / Point clouds / Shape and surface completion

ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds

Gopal Sharma, Difan Liu, Subhransu Maji, Evangelos Kalogerakis, Siddhartha Chaudhuri, Radomír Měch

ECCV 2020 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 177 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add patch distance loss to control-point loss (ablation)SplineNet · SplineDataset open B-splines (with upsampling)Chamfer distance (x100): 2.04 -> 1.96Improved
add patch distance loss to control-point loss (ablation)SplineNet · SplineDataset closed B-splines (with upsampling)Chamfer distance (x100): 5.04 -> 4.9Improved
add Laplacian loss to cp and dist losses (ablation)SplineNet · SplineDataset open B-splines (with upsampling)Chamfer distance (x100): 1.96 -> 1.68Improved
add Laplacian loss to cp and dist losses (ablation)SplineNet · SplineDataset closed B-splines (with upsampling)Chamfer distance (x100): 4.9 -> 3.74Improved
add post-process optimization to SplineNet (ablation)SplineNet · SplineDataset open B-splines (with upsampling)Chamfer distance (x100): 1.68 -> 0.92Improved
add post-process optimization to SplineNet (ablation)SplineNet · SplineDataset closed B-splines (with upsampling)Chamfer distance (x100): 3.74 -> 0.63Improved
add input upsampling for closed B-splines (ablation)SplineNet · SplineDataset closed B-splinesChamfer distance (x100): 3.93 -> 5.04Mixed
add end-to-end joint training of decomposition and fitting (ablation)ParSeNet · ABCPartsseg mIoU: 81.20 -> 82.14Improved
add end-to-end joint training of decomposition and fitting (ablation)ParSeNet · ABCPartsresidual error (all): 0.0120 -> 0.0118Improved
add post-process optimization after end-to-end training (ablation)ParSeNet · ABCPartsresidual error (all): 0.0118 -> 0.0111Improved
add point normals to point input (ablation)ParSeNet · ABCPartsseg mIoU: 71.32 -> 81.20Improved
use ParSeNet instead of SPFN with points and normalsParSeNet + e2e · ABCPartsseg mIoU: 69.01 -> 82.14Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy